Application of information criteria for the selection of statistical fast fading model of the radio mobile channel

Modeling of the reason why several electromagnetic phenome of statistical distribution context, our problematic with radio channel behav years. Thus, the Kolmogo usually employed by the other approaches like probability density functi are obtained empirically propose approaches allo approaches are based on stable with the optimal hi reliable than the KS test . Pereira, G. Coq, X. Li, Y. Pousset, C. Olivier, . Alata, R. Vauzelle, M. Arnaudon and P. Combeau Application of Information Criteria for the Selection of the Statistical small scale Fading Model of the Radio Mobile Channel RE CNRS 3167 TELECOM Bretagne/Departement Micro-Ondes Technopole Brest REST Cedex 3 (France) s and Applications (LMA), University of Poitiers, UMR CNRS n°6086, Teleport 2 Bvd . 30179 86962 Futuroscope Chasseneuil Cedex (France) unications (SIC) Laboratory, University of Poitiers, UMR CNRS n° 6172 Bât. SP2MI Pierre Curie B.P. 30179 86962 Futuroscope Chasseneuil Cedex (France) Xiang.li, pousset, olivier, alata, vauzelle, combeau}@sic.sp2mi.univ-poitiers.fr .coq, Marc.Arnaudon}@math.univ-poitiers.fr radio channel behavior is very important for digital communication. It is propagation models have been implemented to take into account the na inherent to the radio wave channel. So, among these models is the family s, fast in computation time, to describe channel fast fading. In this study is to find among the different statistical laws the one which best coincides ior. Different research has been realized on this subject over about twenty rov-Smirnov (KS) test using Cumulative Distribution Functions (CDF) is radio mobile community partly for its simplicity. Nevertheless, there exist Kulback-Leibler (KL) divergence, which consider distances between ons that may be respresented as histograms. The bins of those histograms i.e. the bins are same size and their number is arbitrary. The authors wing optimal histograms in terms of number and size of bins. These Information Criteria and we show the KL discriminative method is more stograms than with the empirical one. Moreover, our approaches are more whatever the number of considered samples. This last point is directly

[1]  George K. Karagiannidis,et al.  Channel capacity and second-order statistics in Weibull fading , 2004, IEEE Communications Letters.

[2]  R. Nishii.  Maximum likelihood principle and model selection when the true model is unspecified , 1988 .

[3]  M. Salazar-Palma,et al.  A survey of various propagation models for mobile communication , 2003 .

[4]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[5]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[6]  Yannis Pousset,et al.  Outdoor and indoor channel characterization by a 3D simulation software , 2001, 12th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications. PIMRC 2001. Proceedings (Cat. No.01TH8598).

[7]  Jorma Rissanen,et al.  Density estimation by stochastic complexity , 1992, IEEE Trans. Inf. Theory.

[8]  George K. Karagiannidis,et al.  Gaussian class multivariate Weibull distributions: theory and applications in fading channels , 2005, IEEE Transactions on Information Theory.

[9]  Yves Rozenholc,et al.  How many bins should be put in a regular histogram , 2006 .

[10]  Mark A. Pitt,et al.  Advances in Minimum Description Length: Theory and Applications , 2005 .

[11]  Andrea Goldsmith,et al.  Wireless Communications , 2005, 2021 15th International Conference on Advanced Technologies, Systems and Services in Telecommunications (TELSIKS).

[12]  Ali Abdi,et al.  On the estimation of the K parameter for the Rice fading distribution , 2001, IEEE Communications Letters.

[13]  Zhengqing Yun,et al.  Propagation prediction models for wireless communication systems , 2002 .

[14]  Athanasios Papoulis,et al.  Probability, Random Variables and Stochastic Processes , 1965 .